Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1472 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1733091 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1221831 (The Pile)

Max Activating Token Index: 834

Text #2

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3149. Min Act: -0.0000

Data Index: 18810 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1136004 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1040669 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2286. Min Act: -0.0000

Data Index: 593378 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2308. Min Act: -0.0000

Data Index: 36376 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1031678 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2238. Min Act: -0.0000

Data Index: 804166 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2256. Min Act: -0.0000

Data Index: 166221 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1566941 (The Pile)

Max Activating Token Index: 436

Text #11

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1967. Min Act: -0.0000

Data Index: 704169 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1563879 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1876. Min Act: -0.0000

Data Index: 26161 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1860. Min Act: -0.0000

Data Index: 986070 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1749. Min Act: -0.0000

Data Index: 60764 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1919. Min Act: -0.0000

Data Index: 196569 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1795387 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1255302 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1807. Min Act: -0.0000

Data Index: 716553 (The Pile)

Max Activating Token Index: 179